© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 20714
    Prev
    Next
    INDEX
    Explanations

    numerical ratios or specific mathematical relationships

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ratios and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gotten
    -0.90
    dream
    -0.81
    inelli
    -0.76
    uggage
    -0.74
    ORD
    -0.68
    ART
    -0.68
    cart
    -0.67
    stra
    -0.66
    asts
    -0.66
     largeDownload
    -0.65
    POSITIVE LOGITS
     ratios
    1.03
     ratio
    1.00
    xual
    0.98
    yip
    0.93
     mismatch
    0.88
     numer
    0.85
    nces
    0.74
     sum
    0.73
     imbalance
    0.73
    terness
    0.70
    Activations Density 0.013%

    No Known Activations